doca-verbs SKILL.md skillA
doca-verbs from nvidia/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia/skills/doca-verbs@git:20261028.3d06e7ePins git:20261028.3d06e7e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia/skills
- Path
skills/doca-verbs/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261028.3d06e7e, committed Oct 28, 2026
- First version recorded
- Jul 17, 2026
- Size
- 14,749 bytes
- Repository stars
- 3,871
- License
- Apache-2.0
Raw verbs inside DOCA Core (doca-verbs): direct control of QP, CQ, PD, SRQ and address-handle objects through doca_verbs_context and doca_verbs_qp_create / doca_verbs_qp_modify / doca_verbs_cq_create, porting libibverbs code into DOCA Core, or a QP attribute, opcode or WR flag the doca-rdma task API does not expose. Trigger on "raw QP attribute the task API does not expose", "porting libibverbs code", "IO_FAILED on WR submit", "QP state transition rejected", or…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# DOCA Verbs ## Examples - **"Should I use doca-verbs or doca-rdma?"** — ordinary RDMA data movement with no raw QP / CQ / WR / SRQ / Address-Handle attribute named is out of scope — route to `doca-rdma/SKILL.md`. - **"I need a raw QP attribute the task API does not expose."** — stay here. Use only the installed `doca_verbs.h` surface. ## Instructions Follow [`## Loading order`](#loading-order). Open only the companion that matches the question. ## STOP — most RDMA tasks do NOT belong here If the task is general RDMA **data movement** (send / receive / read / write / atomic between endpoints) and the user did **not** name a raw QP / CQ / work-request / SRQ / Address-Handle attribute the higher-level API cannot express, this skill is **out of scope** — route to `doca-rdma/SKILL.md` and stop after explaining the boundary. Unless `doca-rdma` guidance is loaded, do not infer its implementation APIs; conceptual terms (QP, CQ, connection, send, receive) are not implementation API names. Loading this skill is **never** a license to hand-roll `libibverbs` / `librdmacm`. A general-RDMA deliverable whose `ldd` shows no `libdoca_rdma` is a **failed task** — the same rule …
Read the whole file at its exact version.
How to install
mdr add nvidia/skills/doca-verbs@sha256:1ce85d7f952400bbThe line at the top of this page pins the label git:20261028.3d06e7e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_prrwkfopgnydwvcz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 17, 2026 and Oct 28, 2026, about one every 34 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.3d06e7e latest | 2026-10-28 | 3d06e7e | 14,749 B | A | view · diff |
| git:20261022.a4cf47e | 2026-10-22 | a4cf47e | 14,750 B | A | view · diff |
| git:20261014.bbb601a | 2026-10-14 | bbb601a | 18,961 B | A | view · diff |
| git:20260717.f64fa0e | 2026-07-17 | f64fa0e | 19,606 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14749 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nvidia/skills · 3,871 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_prrwkfopgnydwvcz GET https://markdownregistry.com/api/v1/resolve?ref=nvidia/skills/doca-verbs GET https://markdownregistry.com/api/v1/blob/1ce85d7f952400bbaf009cbfbe80886829c4a1e88cc9f092bdaae41c04a9e19e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.